© 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. 14482
    Prev
    Next
    INDEX
    Explanations

    addresses

    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
    1343
    +0.15
    0.4%
    609
    +0.12
    0.4%
    208
    +0.09
    0.3%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    609
    +0.15
    0.02
    1343
    +0.12
    0.02
    1309
    +0.09
    0.01
    Negative Logits
     unspeak
    -1.85
     disreg
    -1.47
     indescri
    -1.45
     vainly
    -1.44
     impelled
    -1.44
     philosophic
    -1.36
     sophistic
    -1.36
     ineffec
    -1.34
     poetical
    -1.30
     apprehen
    -1.30
    POSITIVE LOGITS
     alkoh
    1.56
     drap
    1.55
    <bos>
    1.55
     utop
    1.52
     Kategor
    1.51
     solidar
    1.45
     frans
    1.44
     bronz
    1.44
     spont
    1.40
     gesta
    1.39
    Activations Density 0.030%

    No Known Activations