© 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. 2335
    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
    +0.21
    0.7%
    349
    +0.05
    0.2%
    1225
    +0.05
    0.2%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    2
    -0.21
    0.00
    0
    -0.05
    0.00
    1
    -0.05
    0.00
    Negative Logits
    Gdy
    -0.76
    Wię
    -0.70
    Kiedy
    -0.69
    Wszyst
    -0.66
    Warto
    -0.66
    Teraz
    -0.64
    Przed
    -0.63
    Ostat
    -0.63
    Dlaczego
    -0.62
    Bardzo
    -0.61
    POSITIVE LOGITS
    <bos>
    6.94
     dispen
    1.65
     ftu
    1.65
     fta
    1.57
     aen
    1.53
     fup
    1.51
     mef
    1.49
     blos
    1.49
     paff
    1.48
     meis
    1.47
    Activations Density 0.000%

    No Known Activations

    This feature has no known activations.