© 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. 14578
    Prev
    Next
    INDEX
    Explanations

    mentions of physical movements and body parts

    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
    1978
    +0.15
    0.5%
    1336
    +0.12
    0.3%
    394
    +0.11
    0.3%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    1336
    +0.15
    0.07
    1043
    +0.12
    0.05
    301
    +0.11
    0.03
    Negative Logits
    €.
    -0.73
     Kese
    -0.60
     дописавши
    -0.58
     asseg
    -0.57
    Ehrungen
    -0.54
    amsmath
    -0.54
     pertence
    -0.54
     NUKAT
    -0.53
     getNombre
    -0.51
    amssymb
    -0.50
    POSITIVE LOGITS
     swarovski
    0.80
     ecru
    0.75
     paisley
    0.70
     hoody
    0.70
     hairc
    0.68
     cushi
    0.66
    Wird
    0.62
     softshell
    0.59
    Genau
    0.58
     tawny
    0.58
    Activations Density 0.887%

    No Known Activations