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

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports 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. 14625
    Prev
    Next
    INDEX
    Explanations

    terms related to technology and specifications

    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
    478
    +0.11
    0.3%
    678
    +0.10
    0.3%
    1741
    +0.10
    0.3%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    121
    +0.11
    0.05
    678
    +0.10
    0.05
    505
    +0.10
    0.02
    Negative Logits
     Baillargeon
    -0.91
     مرئيه
    -0.80
    पया
    -0.78
     ***!
    -0.78
     opérateur
    -0.73
    FormTagHelper
    -0.72
    OGND
    -0.71
    Trayectoria
    -0.70
     postIndex
    -0.70
     OMIT
    -0.69
    POSITIVE LOGITS
     shenan
    1.50
     impra
    1.41
     intersper
    1.37
     ineffec
    1.36
     encomp
    1.36
     indescri
    1.35
     increa
    1.32
     unspeak
    1.28
     disreg
    1.28
     maneu
    1.26
    Activations Density 0.357%

    No Known Activations