© 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. 13915
    Prev
    Next
    INDEX
    Explanations

    years, numbers, prices, and ranges

    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
    893
    +0.15
    0.5%
    1343
    +0.09
    0.3%
    849
    +0.08
    0.3%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    499
    +0.15
    0.04
    776
    +0.09
    0.04
    1343
    +0.08
    0.04
    Negative Logits
     depic
    -1.04
     philanth
    -1.01
     affor
    -0.97
     guarante
    -0.96
     tolerably
    -0.96
     encomp
    -0.95
     pamph
    -0.93
     unspeak
    -0.91
     endeavouring
    -0.88
     unwarran
    -0.88
    POSITIVE LOGITS
     murales
    0.67
     sò
    0.60
     giuri
    0.59
     melat
    0.58
     tenda
    0.58
     parati
    0.57
     ē
    0.56
     erit
    0.56
     FetchType
    0.55
     gramos
    0.55
    Activations Density 0.144%

    No Known Activations