© 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. 1004
    Prev
    Next
    INDEX
    Explanations

    recipe instructions, specifically steps involving marinating and baking

    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
    1013
    +0.13
    0.4%
    876
    +0.12
    0.4%
    919
    +0.10
    0.3%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    1833
    +0.13
    0.03
    736
    +0.12
    0.03
    919
    +0.10
    0.01
    Negative Logits
     emphat
    -0.85
     embra
    -0.76
     Wikisource
    -0.76
     inconce
    -0.76
     Cfr
    -0.76
     pamph
    -0.76
     Confe
    -0.74
     parma
    -0.74
     Ibidem
    -0.73
     Keny
    -0.72
    POSITIVE LOGITS
     overnight
    0.72
     resourceCulture
    0.62
    Overnight
    0.61
    <bos>
    0.58
     WaitForSeconds
    0.53
     WebDriverWait
    0.52
     Overnight
    0.52
    horesis
    0.52
    oldown
    0.49
    vernight
    0.49
    Activations Density 0.124%

    No Known Activations