© 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. 13928
    Prev
    Next
    INDEX
    Explanations

    emphasized words related to music and sound effects in a review

    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
    1823
    +0.13
    0.4%
    1935
    +0.10
    0.3%
    678
    +0.10
    0.3%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    1823
    +0.13
    0.05
    1935
    +0.10
    0.04
    783
    +0.10
    0.03
    Negative Logits
     himo
    -0.83
     nawr
    -0.64
     frustra
    -0.57
    onViewCreated
    -0.57
    sidemargin
    -0.56
    InputBorder
    -0.56
    PyExc
    -0.56
    KEYCODE
    -0.56
     insuffisamment
    -0.55
     frigor
    -0.55
    POSITIVE LOGITS
     intersper
    1.46
     indestru
    1.40
     impra
    1.34
     encomp
    1.34
     disreg
    1.33
     hairc
    1.33
     increa
    1.29
     maneu
    1.27
     reluct
    1.27
     scrat
    1.26
    Activations Density 0.485%

    No Known Activations