© 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 SAEs
    5. Gemma-2B
    7. Residual Stream
    9. 0-RES-JB
    11. 2084
    Prev
    Next
    INDEX
    Explanations

    words related to locations, such as cities and countries

    oai_token-act-pair · gpt-3.5-turboTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    jbloom/Gemma-2b-Residual-Stream-SAEs/gemma_2b_blocks.0.hook_resid_post_16384_anthropic
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    HuggingFaceFW/fineweb
    Features
    16,384
    Data Type
    torch.float32
    Hook Point
    blocks.0.hook_resid_post
    Architecture
    standard
    Context Size
    1,024
    Dataset
    HuggingFaceFW/fineweb
    Hook Point Layer
    0
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Neuron Alignment
    Index
    Value
    % of L₁
    1871
    +0.09
    0.3%
    629
    +0.09
    0.3%
    382
    +0.07
    0.2%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    1120
    +0.09
    0.07
    1319
    +0.09
    0.07
    690
    +0.07
    0.07
    Negative Logits
    div
    -1.25
    throw
    -1.24
     won
    -1.20
    float
    -1.20
     nach
    -1.19
     aber
    -1.17
     through
    -1.16
    void
    -1.16
    int
    -1.16
     dann
    -1.16
    POSITIVE LOGITS
     increa
    5.12
     squa
    5.06
     fta
    5.01
     desir
    4.88
     secon
    4.83
     fto
    4.81
     aen
    4.78
     effe
    4.78
     fuf
    4.75
     ftu
    4.75
    Activations Density 0.277%

    No Known Activations