© 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
    3. Joseph Bloom · Initial Gemma-2B-IT SAEs
    5. Gemma-2B-IT
    7. Residual Stream
    9. 12-RES-JB
    11. 14087
    Prev
    Next
    INDEX
    Explanations

    Marvel comic book characters, particularly those related to the X-Men franchise

    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
    1124
    +0.15
    0.6%
    1758
    +0.14
    0.6%
    251
    +0.14
    0.6%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    662
    +0.15
    0.03
    1124
    +0.14
    0.03
    1758
    +0.14
    0.03
    Negative Logits
    Då
    -0.58
    PerformLayout
    -0.55
    Natürlich
    -0.53
    FieldBuilder
    -0.52
    Nå
    -0.52
    Varför
    -0.52
    Grüße
    -0.52
    Indented
    -0.51
    GetKeyDown
    -0.49
    Vídeo
    -0.49
    POSITIVE LOGITS
     Xy
    1.02
     Xs
    0.98
     Xanth
    0.97
     Xen
    0.97
     XA
    0.92
     igno
    0.92
     saluto
    0.92
     xer
    0.92
     xt
    0.92
     excu
    0.91
    Activations Density 0.110%

    No Known Activations