© 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. 14457
    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
    +0.38
    1.8%
    1741
    +0.05
    0.2%
    2019
    +0.05
    0.2%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    2
    -0.38
    0.00
    0
    -0.05
    0.00
    1
    -0.05
    0.00
    Negative Logits
     
    -0.88
    ,
    -0.87
     so
    -0.87
     such
    -0.86
     to
    -0.86
     ко
    -0.85
     of
    -0.85
     الأ
    -0.84
     as
    -0.84
     не
    -0.84
    POSITIVE LOGITS
    <bos>
    11.52
     dispen
    3.09
     effe
    3.08
     fta
    3.04
     fte
    2.91
     squa
    2.91
     desir
    2.90
     fuf
    2.89
     perfet
    2.88
     ftu
    2.87
    Activations Density 0.000%

    No Known Activations

    This feature has no known activations.