© 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. 3974
    Prev
    Next
    INDEX
    Explanations

    information related to procedures, requirements, and certifications

    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
    453
    +0.10
    0.3%
    1042
    +0.08
    0.2%
    946
    +0.08
    0.2%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    1889
    +0.10
    0.04
    614
    +0.08
    0.04
    1447
    +0.08
    0.04
    Negative Logits
     incess
    -0.83
     utop
    -0.74
     robus
    -0.68
     saluti
    -0.67
     unifor
    -0.66
     tremb
    -0.66
     idyl
    -0.64
     fuo
    -0.63
     contrari
    -0.63
     companyId
    -0.63
    POSITIVE LOGITS
    <bos>
    0.65
     entry
    0.64
     access
    0.64
     accessing
    0.61
     eligibility
    0.60
    access
    0.58
     admission
    0.53
    entry
    0.52
     entering
    0.51
     participate
    0.51
    Activations Density 0.364%

    No Known Activations