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

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsinterp-engineNEWAPI 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. 5276
    Prev
    Next
    INDEX
    Explanations

    specific configurations related to gaming scenarios, such as unique abilities, movement speeds, and armor penetration

    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
    2019
    +0.25
    0.9%
    876
    +0.20
    0.7%
    678
    +0.18
    0.6%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    876
    +0.25
    0.00
    678
    +0.20
    0.04
    304
    +0.18
    0.01
    Negative Logits
     
    -1.17
    ,
    -1.17
     at
    -1.15
     on
    -1.13
     I
    -1.12
     as
    -1.11
    ↵↵
    -1.10
    .
    -1.10
     of
    -1.09
     for
    -1.09
    POSITIVE LOGITS
     embra
    2.67
     !...
    2.64
     ftu
    2.62
     sovere
    2.62
     magis
    2.60
     dises
    2.60
     inev
    2.59
     volunte
    2.59
     desir
    2.58
     ?...
    2.58
    Activations Density 0.151%

    No Known Activations