© 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. 14473
    Prev
    Next
    INDEX
    Explanations

    percentages and numeric data

    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
    674
    +0.14
    0.4%
    605
    +0.12
    0.3%
    1105
    +0.11
    0.3%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    1105
    +0.14
    0.05
    446
    +0.12
    0.04
    426
    +0.11
    0.04
    Negative Logits
     fto
    -1.17
     wherea
    -1.13
     secon
    -1.13
     parch
    -1.11
     fta
    -1.09
     fortn
    -1.08
     Pyrene
    -1.07
     Daven
    -1.06
     withal
    -1.05
     squa
    -1.04
    POSITIVE LOGITS
    <bos>
    0.85
     percent
    0.74
     resourceCulture
    0.73
     AssemblyVersion
    0.70
     Wikimédia
    0.68
    percent
    0.68
    躇
    0.66
    DeleteBehavior
    0.66
     \%(
    0.65
    setLayoutParams
    0.63
    Activations Density 0.163%

    No Known Activations