© 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. 889
    Prev
    Next
    INDEX
    Explanations

    information related to American football positions, particularly linebackers and defensive positions

    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
    227
    +0.14
    0.4%
    1842
    +0.14
    0.4%
    394
    +0.10
    0.3%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    658
    +0.14
    0.05
    761
    +0.14
    0.04
    1597
    +0.10
    0.03
    Negative Logits
     affez
    -1.14
     dégust
    -1.01
     écout
    -0.99
     riemp
    -0.94
     ricor
    -0.92
     regardant
    -0.91
     ispir
    -0.90
     abbra
    -0.89
     sentito
    -0.89
     effe
    -0.89
    POSITIVE LOGITS
     midfielder
    0.59
     position
    0.53
     midfield
    0.53
     quarterback
    0.52
    úgó
    0.51
     lineman
    0.50
     виправивши
    0.50
     linebacker
    0.49
     teammate
    0.49
    campista
    0.49
    Activations Density 0.244%

    No Known Activations