© 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. 4453
    Prev
    Next
    INDEX
    Explanations

    situations where a consistent line length is specified

    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
    1978
    +0.12
    0.3%
    1343
    +0.11
    0.3%
    460
    +0.10
    0.3%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    1343
    +0.12
    0.07
    609
    +0.11
    0.05
    382
    +0.10
    0.05
    Negative Logits
    Mű
    -0.54
    Periodo
    -0.54
     extreme
    -0.53
    Hvor
    -0.51
    Hvis
    -0.51
    Também
    -0.51
    enumii
    -0.51
    ("]");
    -0.51
    Negocio
    -0.50
    Além
    -0.50
    POSITIVE LOGITS
     desir
    1.53
     nece
    1.51
     dispen
    1.48
     embra
    1.46
     dises
    1.46
     effe
    1.45
     squa
    1.43
     ?...
    1.43
     fep
    1.43
     fto
    1.41
    Activations Density 0.296%

    No Known Activations