© 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. 14209
    Prev
    Next
    INDEX
    Explanations

    the acknowledgment of financial support or funding in research documents

    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
    +0.21
    0.7%
    394
    +0.16
    0.5%
    599
    +0.12
    0.4%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    453
    +0.21
    0.09
    752
    +0.16
    0.05
    16
    +0.12
    0.08
    Negative Logits
    --)
    -0.62
    Và
    -0.62
    lccccc
    -0.61
    lcccccc
    -0.60
    RuleContext
    -0.60
    wikidata
    -0.60
    CopyWith
    -0.58
    IsContent
    -0.57
    Còn
    -0.57
    Nhưng
    -0.57
    POSITIVE LOGITS
     milf
    1.09
     increa
    1.05
     reluct
    1.04
     strick
    1.03
     snoopy
    1.02
     stockholm
    1.01
     affor
    1.00
     scrat
    0.99
     fuf
    0.97
     accla
    0.96
    Activations Density 1.012%

    No Known Activations