© 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. 14345
    Prev
    Next
    INDEX
    Explanations

    corrections or edits in text

    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
    1407
    +0.17
    0.6%
    1896
    +0.11
    0.4%
    1548
    +0.11
    0.4%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    1407
    +0.17
    0.03
    492
    +0.11
    0.02
    1548
    +0.11
    0.02
    Negative Logits
     Audiodateien
    -0.51
    HideInInspector
    -0.51
    FetchType
    -0.51
    andowski
    -0.47
    Xoxo
    -0.43
     MainAxisSize
    -0.42
    
    
    -0.41
    MLLoader
    -0.41
    Kaiser
    -0.41
     Mem
    -0.41
    POSITIVE LOGITS
     corrects
    1.09
     correcting
    1.06
     correction
    1.05
     Correct
    1.04
    CORRECT
    1.04
     corrections
    1.02
     Correction
    1.00
    correction
    1.00
     corrected
    0.99
    correct
    0.97
    Activations Density 0.063%

    No Known Activations