© 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. 13790
    Prev
    Next
    INDEX
    Explanations

    discussions or descriptions focusing on viewpoints or attitudes

    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
    528
    +0.14
    0.5%
    1677
    +0.11
    0.4%
    1233
    +0.10
    0.4%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    528
    +0.14
    0.02
    121
    +0.11
    0.02
    240
    +0.10
    0.02
    Negative Logits
     proprement
    -0.64
     Winf
    -0.61
     enrique
    -0.60
     Oester
    -0.60
     Uli
    -0.59
     idéia
    -0.58
     scatt
    -0.58
     brilla
    -0.57
     reiv
    -0.57
     Mier
    -0.56
    POSITIVE LOGITS
     perspective
    1.46
     perspectives
    1.33
     Perspective
    1.33
    perspective
    1.23
    Perspective
    1.19
     Perspectives
    1.04
    pectives
    1.01
     PERSPECT
    1.01
     viewpoint
    0.96
     perspectiva
    0.94
    Activations Density 0.087%

    No Known Activations