© 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. 967
    Prev
    Next
    INDEX
    Explanations

    quotations and direct speech

    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
    2019
    +0.23
    0.7%
    736
    +0.13
    0.4%
    678
    +0.12
    0.4%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    1404
    +0.23
    0.06
    545
    +0.13
    0.05
    736
    +0.12
    0.06
    Negative Logits
    throwaway
    -0.78
     mécanisme
    -0.77
     maintien
    -0.73
     fameux
    -0.70
     noyau
    -0.67
     Deviant
    -0.65
    <bos>
    -0.62
     lecteur
    -0.61
     réservoir
    -0.59
     recrutement
    -0.59
    POSITIVE LOGITS
     particolar
    1.02
     adulti
    0.93
     utop
    0.93
     felici
    0.89
     venuto
    0.88
     competen
    0.87
     saluto
    0.86
     ideolog
    0.86
    fordable
    0.85
     eccell
    0.84
    Activations Density 0.182%

    No Known Activations