© 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. 3729
    Prev
    Next
    INDEX
    Explanations

    phrases related to survival horror video games

    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
    184
    +0.20
    0.6%
    674
    +0.20
    0.6%
    1842
    +0.16
    0.5%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    184
    +0.20
    0.04
    908
    +0.20
    0.02
    1438
    +0.16
    0.03
    Negative Logits
     prét
    -0.67
     Cfr
    -0.67
     firent
    -0.67
     Ibidem
    -0.66
    lxt
    -0.65
     Atm
    -0.65
     exorbit
    -0.65
     éprou
    -0.64
     CrossRef
    -0.64
     Nema
    -0.63
    POSITIVE LOGITS
     had
    0.76
     knew
    0.75
     hadn
    0.75
     was
    0.74
     wasn
    0.73
     seemed
    0.73
     mattered
    0.71
     weren
    0.70
     were
    0.70
     belonged
    0.69
    Activations Density 0.536%

    No Known Activations