© 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. 3444
    Prev
    Next
    INDEX
    Explanations

    positive adjectives describing different aspects of a product or service

    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
    1870
    +0.13
    0.4%
    382
    +0.10
    0.3%
    1253
    +0.10
    0.3%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    1867
    +0.13
    0.05
    1147
    +0.10
    0.05
    1935
    +0.10
    0.05
    Negative Logits
     exemplaire
    -1.13
     itinéraire
    -1.11
     clôture
    -1.02
     appui
    -1.01
     héro
    -1.00
     étrang
    -0.98
     merveilleux
    -0.98
     coté
    -0.96
     nuage
    -0.96
     épis
    -0.94
    POSITIVE LOGITS
     reminder
    0.70
     source
    0.68
     thing
    0.67
     contribution
    0.63
     indication
    0.61
     example
    0.61
     contributor
    0.60
     result
    0.60
     way
    0.59
     consideration
    0.58
    Activations Density 0.300%

    No Known Activations