© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW
    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI 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. 4055
    Prev
    Next
    INDEX
    Explanations

    scenes of violence and aftermath in a setting like a house or town

    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
    906
    +0.16
    0.5%
    946
    +0.08
    0.2%
    198
    +0.08
    0.2%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    736
    +0.16
    0.07
    946
    +0.08
    0.06
    724
    +0.08
    0.04
    Negative Logits
     ecru
    -1.09
     hairc
    -1.01
     fré
    -0.81
     paisley
    -0.80
     cushi
    -0.78
     unspeak
    -0.78
     silken
    -0.78
     Whence
    -0.78
     emphat
    -0.77
     tupperware
    -0.77
    POSITIVE LOGITS
     broken
    0.60
     missing
    0.57
    痕
    0.57
     indicating
    0.56
     evidence
    0.54
     residue
    0.54
     تضيفلها
    0.53
    missing
    0.53
     visible
    0.52
     overturned
    0.51
    Activations Density 0.465%

    No Known Activations