© 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. 13019
    Prev
    Next
    INDEX
    Explanations

    references to technical programming concepts related to coding structures and syntax

    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
    50
    +0.30
    1.1%
    1741
    +0.28
    1.1%
    2019
    +0.20
    0.8%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    50
    +0.30
    0.08
    16
    +0.28
    0.10
    1959
    +0.20
    0.08
    Negative Logits
     oeil
    -0.62
     contemporánea
    -0.60
     Halen
    -0.60
     įsi
    -0.59
     couteau
    -0.57
     hiburan
    -0.56
     doigt
    -0.56
     contemporáneo
    -0.55
     ruban
    -0.55
    ෘ
    -0.55
    POSITIVE LOGITS
     mef
    1.28
     effe
    1.25
     aen
    1.22
     erec
    1.21
     meis
    1.18
     oleo
    1.16
     nece
    1.15
     „,
    1.14
     wien
    1.14
     levis
    1.12
    Activations Density 0.539%

    No Known Activations