© 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. 14213
    Prev
    Next
    INDEX
    Explanations

    URL links with query parameters

    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
    1224
    +0.14
    0.4%
    1343
    +0.14
    0.4%
    453
    +0.14
    0.4%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    1224
    +0.14
    0.02
    1478
    +0.14
    0.02
    1021
    +0.14
    0.02
    Negative Logits
     minValue
    -0.71
     currentValue
    -0.65
     maxn
    -0.65
     maxValue
    -0.63
     startX
    -0.61
     rval
    -0.61
     currentNode
    -0.60
     Overcome
    -0.58
     McLaugh
    -0.57
     maxX
    -0.57
    POSITIVE LOGITS
     stili
    0.98
     medes
    0.97
     abbra
    0.97
     peculi
    0.97
     affez
    0.96
     inol
    0.95
     bont
    0.90
     Settembre
    0.90
     perche
    0.90
     espri
    0.89
    Activations Density 0.031%

    No Known Activations