© 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
    2. Joseph Bloom · Initial Gemma-2B-IT SAEs
    3. Gemma-2B-IT
    4. Residual Stream
    5. 12-RES-JB
    6. 12859
    Prev
    Next
    INDEX
    Explanations

    dates in historical context

    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
    1614
    +0.12
    0.3%
    1870
    +0.11
    0.3%
    1741
    +0.10
    0.3%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    1614
    +0.12
    0.07
    841
    +0.11
    0.04
    1934
    +0.10
    0.04
    Negative Logits
     sophistic
    -0.78
     vicissitudes
    -0.75
     salutary
    -0.75
     resemb
    -0.75
     tolerably
    -0.73
     philosophic
    -0.71
     caprice
    -0.70
     impractica
    -0.70
     unspeak
    -0.70
     impra
    -0.69
    POSITIVE LOGITS
     alkoh
    1.51
     parati
    1.51
     makro
    1.50
     moza
    1.45
     elek
    1.44
     plak
    1.43
     utop
    1.43
     karton
    1.39
     lampa
    1.38
     meras
    1.38
    Activations Density 0.083%

    No Known Activations