© 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 EvalsExportsAPI 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. 11242
    Prev
    Next
    INDEX
    Explanations

    references to software coding and development

    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
    964
    +0.30
    1.2%
    1343
    +0.22
    0.9%
    856
    +0.18
    0.7%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    198
    +0.30
    0.05
    964
    +0.22
    0.04
    764
    +0.18
    0.03
    Negative Logits
    <bos>
    -0.97
     bezeichneter
    -0.70
    };*/
    -0.55
    Geografía
    -0.55
    Descripció
    -0.53
    зулта
    -0.53
    intios
    -0.53
    })();
    -0.51
    InputTagHelper
    -0.50
    ArrowToggle
    -0.50
    POSITIVE LOGITS
     maneu
    0.82
     affor
    0.81
     scrat
    0.76
     gaily
    0.74
     milf
    0.73
     guarante
    0.73
     greate
    0.72
     squa
    0.72
     hentai
    0.72
     apprehen
    0.71
    Activations Density 0.359%

    No Known Activations