© 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. 2466
    Prev
    Next
    INDEX
    Explanations
    No Explanations Found
    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
    674
    +0.30
    1.0%
    1741
    +0.07
    0.2%
    394
    +0.06
    0.2%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    2
    -0.30
    0.00
    0
    -0.07
    0.00
    1
    -0.06
    0.00
    Negative Logits
    ("="
    -0.61
    ])]
    -0.60
    ्रीन
    -0.56
     eset
    -0.55
    mbolic
    -0.55
    COMO
    -0.55
     gunmen
    -0.55
    )]=
    -0.55
     против
    -0.54
    )}=\
    -0.54
    POSITIVE LOGITS
    <bos>
    6.93
     ftu
    1.80
     effe
    1.79
     dispen
    1.75
     embra
    1.75
     fto
    1.71
     fta
    1.71
     fuf
    1.69
     !...
    1.69
     fte
    1.69
    Activations Density 0.000%

    No Known Activations

    This feature has no known activations.