© 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
    3. Joseph Bloom · Initial Gemma-2B-IT SAEs
    5. Gemma-2B-IT
    7. Residual Stream
    9. 12-RES-JB
    11. 13397
    Prev
    Next
    INDEX
    Explanations

    mentions of technology details and hardware specifications

    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
    227
    +0.12
    0.3%
    678
    +0.11
    0.3%
    604
    +0.10
    0.3%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    678
    +0.12
    0.05
    1446
    +0.11
    0.02
    181
    +0.10
    0.03
    Negative Logits
    <bos>
    -0.82
    UnitTesting
    -0.79
     pamph
    -0.70
    IsContent
    -0.67
    InjectAttribute
    -0.63
    EndContext
    -0.63
    OGND
    -0.62
    StoryboardSegue
    -0.62
     يتيمه
    -0.60
    AnchorStyles
    -0.59
    POSITIVE LOGITS
     [''
    0.85
     considér
    0.72
     affez
    0.65
     cerchi
    0.64
     éprou
    0.64
     trouva
    0.64
     surpl
    0.63
     lusso
    0.63
     obé
    0.63
     merav
    0.62
    Activations Density 0.279%

    No Known Activations