© 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. 7598
    Prev
    Next
    INDEX
    Explanations

    phrases related to abilities or actions that can or cannot be done

    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
    1387
    +0.12
    0.4%
    674
    +0.11
    0.4%
    214
    +0.09
    0.3%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    1415
    +0.12
    0.05
    1974
    +0.11
    0.05
    1387
    +0.09
    0.05
    Negative Logits
     Micho
    -0.72
     hcm
    -0.67
     jaya
    -0.67
     Alcalde
    -0.67
     Româ
    -0.66
    Opere
    -0.65
     Cuer
    -0.65
     Sinal
    -0.65
     Glou
    -0.63
     Abbé
    -0.63
    POSITIVE LOGITS
    <bos>
    0.77
     afford
    0.72
    
    
    0.68
    desertcart
    0.63
    can
    0.62
     can
    0.62
     safely
    0.61
    Kann
    0.60
    ⓧ
    0.58
    <?
    0.57
    Activations Density 0.218%

    No Known Activations