© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW
    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI 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. 14380
    Prev
    Next
    INDEX
    Explanations

    tokens related to coding in Rust and accelerometer sensor reading

    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
    1871
    +0.26
    0.9%
    876
    +0.22
    0.8%
    304
    +0.19
    0.6%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    1871
    +0.26
    0.05
    678
    +0.22
    0.04
    304
    +0.19
    0.01
    Negative Logits
     for
    -1.25
     in
    -1.23
     
    -1.23
     at
    -1.21
    ,
    -1.19
     to
    -1.19
     on
    -1.18
     and
    -1.18
    <bos>
    -1.18
     of
    -1.16
    POSITIVE LOGITS
     wien
    3.39
     mef
    3.35
     napoli
    3.27
     dises
    3.26
     !...
    3.23
     milano
    3.23
     meis
    3.21
     ?...
    3.20
     aen
    3.18
     doman
    3.17
    Activations Density 0.135%

    No Known Activations