© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW
    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    2. Joseph Bloom · Initial Gemma-2B-IT SAEs
    3. Gemma-2B-IT
    4. Residual Stream
    5. 12-RES-JB
    6. 6565
    Prev
    Next
    INDEX
    Explanations

    strings for string manipulation and formatting operations, such as joining strings together and formatting variables in a certain way

    oai_token-act-pair · gpt-3.5-turboTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    jbloom/Gemma-2b-IT-Residual-Stream-SAEs/gemma_2b_it_blocks.12.hook_resid_post_16384
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    HuggingFaceFW/fineweb
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.12.hook_resid_post
    Hook Layer
    12
    Architecture
    standard
    Context Size
    1,024
    Dataset
    Skylion007/openwebtext
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Neuron Alignment
    Index
    Value
    % of L₁
    1967
    +0.22
    0.7%
    1343
    +0.17
    0.6%
    674
    +0.16
    0.5%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    1265
    +0.22
    0.03
    876
    +0.17
    -0.00
    1771
    +0.16
    0.03
    Negative Logits
    полнитель
    -0.52
     Breslau
    -0.50
     مشين
    -0.49
     unavoid
    -0.47
     thunderbolt
    -0.46
    BeginInit
    -0.46
    беріга
    -0.46
     Necro
    -0.45
     conspicuously
    -0.45
     Lübeck
    -0.45
    POSITIVE LOGITS
     Ottobre
    0.89
     Giugno
    0.79
     soste
    0.78
     affez
    0.76
     vola
    0.75
     Luglio
    0.73
     apparti
    0.73
     Settembre
    0.72
     natale
    0.71
     soggior
    0.70
    Activations Density 0.135%

    No Known Activations