© 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. 2507
    Prev
    Next
    INDEX
    Explanations

    descriptions of strange or unusual behaviors

    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
    198
    +0.10
    0.3%
    1553
    +0.10
    0.3%
    604
    +0.10
    0.3%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    736
    +0.10
    0.08
    1553
    +0.10
    0.07
    1419
    +0.10
    0.05
    Negative Logits
    <bos>
    -1.03
     Outils
    -0.76
     mû
    -0.74
     dovr
    -0.72
     FBref
    -0.68
     déchir
    -0.68
     Mga
    -0.67
     disambiguazione
    -0.66
     vettoriale
    -0.66
     serai
    -0.65
    POSITIVE LOGITS
     excessively
    0.63
     incoherent
    0.62
     incessant
    0.60
     constantly
    0.60
     incessantly
    0.58
    Cześć
    0.58
     loudly
    0.57
     erratic
    0.56
     getCustomer
    0.56
     repeatedly
    0.56
    Activations Density 0.869%

    No Known Activations