© 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. 7569
    Prev
    Next
    INDEX
    Explanations

    verbs relating to taking action or causing change

    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
    405
    +0.11
    0.4%
    1296
    +0.11
    0.4%
    674
    +0.10
    0.3%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    405
    +0.11
    0.06
    1296
    +0.11
    0.05
    662
    +0.10
    0.05
    Negative Logits
    getLastName
    -0.70
    isDebugEnabled
    -0.57
    getClassName
    -0.56
    audiovisuel
    -0.55
     للمعارف
    -0.51
    getFirstName
    -0.51
    getNome
    -0.47
    getNombre
    -0.46
     июля
    -0.45
     StringUtil
    -0.45
    POSITIVE LOGITS
     getty
    0.94
     poichè
    0.90
     GETTING
    0.86
     GETS
    0.79
     migli
    0.79
     jared
    0.77
    GETTING
    0.77
     alaska
    0.77
     gotten
    0.76
     aiuta
    0.76
    Activations Density 0.149%

    No Known Activations