© 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. 14156
    Prev
    Next
    INDEX
    Explanations

    names and nicknames of individuals, particularly in sports contexts

    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
    964
    +0.12
    0.4%
    1343
    +0.12
    0.3%
    1842
    +0.09
    0.3%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    981
    +0.12
    0.05
    1597
    +0.12
    0.03
    227
    +0.09
    0.04
    Negative Logits
    CLUDING
    -0.65
    PLICATIONS
    -0.61
    PONENTS
    -0.61
     asado
    -0.60
    FORMANCE
    -0.58
     powinno
    -0.52
     ważne
    -0.51
     powinna
    -0.51
     korzyst
    -0.50
    roaches
    -0.50
    POSITIVE LOGITS
     »>
    1.14
     alkoh
    1.13
     ftre
    1.11
     Gouver
    1.11
     kosme
    1.10
     ftu
    1.09
     keramik
    1.08
     Lombar
    1.05
     Chapitre
    1.04
     fup
    1.04
    Activations Density 0.269%

    No Known Activations