© 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. 14409
    Prev
    Next
    INDEX
    Explanations

    descriptions of physical characteristics or properties

    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
    964
    +0.15
    0.5%
    184
    +0.14
    0.4%
    50
    +0.13
    0.4%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    736
    +0.15
    0.06
    184
    +0.14
    0.02
    2044
    +0.13
    0.06
    Negative Logits
     praktik
    -0.99
     Rektor
    -0.90
     ideolog
    -0.90
     meras
    -0.88
     minimalis
    -0.86
     kosme
    -0.85
     alkoh
    -0.83
     notor
    -0.82
     solidar
    -0.82
     Gouver
    -0.80
    POSITIVE LOGITS
     ecru
    1.42
     swarovski
    1.40
     hairc
    1.39
     disagre
    1.34
     impractica
    1.25
     shenan
    1.21
     apprehen
    1.20
     scrat
    1.19
     reluct
    1.17
     indestru
    1.17
    Activations Density 0.544%

    No Known Activations